1. What is the main idea of the paper? (you can get much information on this from the abstract and introduction)
2. What experiment, if any, was performed?
3. Was the experiment (or, if one was not performed, the data presented) GS or BS? That is, was there a large sample size, a cause-and-effect relationship, etc.
4. What did the authors determine about forensic graphology?
5. Name at least five interesting facts from the paper that you think the rest of the class might appreciate.
The main idea of the paper is to identify handwriting. Many people think that many of the techniques have been reported for handwriter identification. The majority of techniques are assumed that the written text is fixed. Also, they were trying to figure out a computer program that would figure out if the handwriting was the same or different. The experiment that they performed was to focus on two streams of handwriting identification (off-line and on-line handwriting identification). On-line writer identification techniques are not well developed (as compared to on-line signature verification methods), and only a few papers have been published on this subject. In comparison, off-line systems have been studied either as fully automated tools or as interactive tools. These systems are based on the use of computer image processing and pattern recognition techniques to solve the different types of problems encountered for example: pre-processing, feature extraction and selection, specimen comparison and performance evaluation. The experiment that was performed is GS. There was a large sample size and cause-and-effect relationship. The authors determined that forensic graphology is that the handwriting of different people is visually distinctive and a global approach based on textures analysis can be adopted. 1. A number of experiments have been conducted with 40 different writer classes. 2. The results contained an accuracy of 96.0%.
Misti Rose Whitfield
Handwriting Identification.
1. What is the main idea of the paper? (you can get much information on this from the abstract and introduction)
2. What experiment, if any, was performed?
3. Was the experiment (or, if one was not performed, the data presented) GS or BS? That is, was there a large sample size, a cause-and-effect relationship, etc.
4. What did the authors determine about forensic graphology?
5. Name at least five interesting facts from the paper that you think the rest of the class might appreciate.
The main idea of the paper is to identify handwriting. Many people think that many of the techniques have been reported for handwriter identification. The majority of techniques are assumed that the written text is fixed. Also, they were trying to figure out a computer program that would figure out if the handwriting was the same or different. The experiment that they performed was to focus on two streams of handwriting identification (off-line and on-line handwriting identification). On-line writer identification techniques are not well developed (as compared to on-line signature verification methods), and only a few papers have been published on this subject. In comparison, off-line systems have been studied either as fully automated tools or as interactive tools. These systems are based on the use of computer image processing and pattern recognition techniques to solve the different types of problems encountered for example: pre-processing, feature extraction and selection, specimen comparison and performance evaluation. The experiment that was performed is GS. There was a large sample size and cause-and-effect relationship. The authors determined that forensic graphology is that the handwriting of different people is visually distinctive and a global approach based on textures analysis can be adopted. 1. A number of experiments have been conducted with 40 different writer classes. 2. The results contained an accuracy of 96.0%.